© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57263
    Prev
    Next
    INDEX
    Explanations

    compound names or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦæŶåĢĻä¸Ģå®ļè¦ģ
    -0.07
    amed
    -0.07
    ery
    -0.07
    epak
    -0.07
    ลู
    -0.06
    ãĥ¬ãĥ¼ãĤ·ãĥ§ãĥ³
    -0.06
    è®¤è®¤çľŁçľŁ
    -0.06
    hec
    -0.06
    ลà¹Į
    -0.06
    pte
    -0.06
    POSITIVE LOGITS
     Fucking
    0.08
    AndWait
    0.08
    ฯ
    0.07
    **–
    0.07
    å·¨æĺŁ
    0.06
    goo
    0.06
    OrNil
    0.06
    æīĭéĩĮ
    0.06
    ToLocal
    0.06
    ówki
    0.06
    Activations Density 0.803%

    No Known Activations